Graphiti MCP
Graphiti MCP Server
Zep's Graphiti MCP server: long-term agent memory as a time-aware knowledge graph on FalkorDB or Neo4j
- 32,326 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- Sends episode content to an external LLM provider
- Runs database containers
Install
- Works in
Manual install
git clone https://github.com/getzep/graphiti.git
cd graphiti/mcp_server
docker compose upStarts FalkorDB and the MCP server in one container. Set your LLM provider key first.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Sends episode content to an external LLM provider
- Runs database containers
This is third-party code. Review the repository files before installing.
What it does
Graphiti builds a knowledge graph that grows from conversations, documents and JSON and keeps the history of how facts change. The MCP server in mcp_server gives the agent tools to add episodes, find facts and entities with semantic and hybrid search, group data by group_id and maintain the graph. Typed entities are extracted from text: preferences, requirements, procedures, organizations, events and more. Episodes are processed in a queue with configurable concurrency.
Who it is for. For developers who need their agent to remember context across sessions and projects.
Good fit when
- The agent needs long-term memory of user preferences and project decisions
- You need to track how facts changed over time
- You already use Neo4j or can run a FalkorDB container
Not a fit when
- A simple notes file or CLAUDE.md is enough
- You cannot afford many LLM calls during ingestion
Example request
Remember that this project uses pnpm and we never touch the legacy folderMCP
- Transport
- http
- Authentication
- API key
Environment variables
OPENAI_API_KEYrequired, secret- Default LLM provider key; another provider needs its own key
NEO4J_URI- Neo4j address when used instead of FalkorDB
NEO4J_PASSWORDsecret- Neo4j password
SEMAPHORE_LIMIT- How many episodes to process concurrently
Limitations
The server is marked experimental. It needs Docker or Python 3.10+ with uv and an LLM provider key, OpenAI by default; Ollama is supported. Each episode takes several model calls, and small local models often break structured output.
How to disable. Stop the docker compose containers and remove the graphiti-memory server from your MCP client config.
FAQ
Which database should I pick?
FalkorDB ships in the same container as the server by default. The README recommends Neo4j for production.
Can I avoid OpenAI?
Yes, Anthropic, Gemini, Groq, Azure OpenAI and OpenAI-compatible endpoints like Ollama are supported.
Discussion
No questions or reviews yet.
Related
MCP serversAn MCP memory server for agents built on a knowledge graph: relevance as an evidence path, not just vector similarity
Self-hosted long-term memory for agents: semantic search, a knowledge graph and autonomous consolidation over MCP and a REST API
Knowledge-graph memory for agents: Claude Code and Codex plugins, an MCP server and a Python library
An MCP server for long-term agent memory: compresses dialogues into atomic facts, resolves pronouns and anchors relative time to absolute dates
MCP Knowledge Graph
mcp-knowledge-graph
Persistent memory for AI in a local knowledge graph: entities, relations and observations are stored in .aim files on your disk
A self-hosted MCP server for long-term agent memory: structured records, versioned rollback and a visual dashboard
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Graphiti MCP (this entry) | no | API key | 32,326 | |
| Omnigraph | yes | API key | 1,801 | a graph database with git-style branches |
| Lemmalog | no | not required | 341 | a Datalog engine in Rust as an agent's working memory |
| Caura | yes | API key | 535 | shared memory for fleets of AI agents with access scopes |
README in short
The server README explains how Graphiti differs from plain RAG and lists the MCP features. The quick start uses docker compose with FalkorDB or a separate Neo4j setup, plus a uv-based config for stdio-only clients. It details config.yaml: database, model and embedding providers, entity types and concurrency limit. Apache-2.0 licensed.